diff options
| -rw-r--r-- | README.md | 8 | ||||
| -rw-r--r-- | nerv/doc/nerv.md | 6 | ||||
| -rw-r--r-- | nerv/doc/nerv_class.md | 8 | ||||
| -rw-r--r-- | nerv/doc/nerv_io.md | 13 | ||||
| -rw-r--r-- | nerv/doc/nerv_layer.md | 13 | ||||
| -rw-r--r-- | nerv/doc/nerv_matrix.md | 14 | ||||
| -rw-r--r-- | nerv/doc/nerv_nn.md | 43 | ||||
| -rw-r--r-- | nerv/doc/nerv_param.md | 10 |
8 files changed, 60 insertions, 55 deletions
@@ -1,9 +1,9 @@ -#The Nerv Toolkit User Manual# +# The Nerv Toolkit User Manual NOTE: This readme is obsolete and will be rearranged, for further information, please check http://nerv-sjtu.github.io/nerv/ This user manual will information about how to use __Nerv__ and __Nerv__'s interface. -##How to make and start using## +## How to make and start using First make sure you have __lua__ and __CUDA__ installed on your computer. __Nerv__ is currently developed via github.You can download and make __Nerv__ by doing the following: ``` @@ -29,11 +29,11 @@ You need to be at or (copy files from) `/slfs1`(SJTU speechlab cluster) to get t ./install/bin/nerv nerv/examples/asr_trainer.lua nerv/examples/swb_baseline.lua ``` -##How to contribute## +## How to contribute Fork the original repository, then use the __pull&merge__ function in github to contribute. The pull&merge request can be found on your dashboard in github. See this [sync-help] to sync with the original repository. -##Nerv Packages## +## Nerv Packages * __luaT__ Nerv uses [luaT]\(a [Torch] library\) to define lua class in C. * __[The Nerv OOP](nerv/doc/nerv_class.md)__ diff --git a/nerv/doc/nerv.md b/nerv/doc/nerv.md index 28411f5..125928d 100644 --- a/nerv/doc/nerv.md +++ b/nerv/doc/nerv.md @@ -1,6 +1,6 @@ -#The Nerv utility functions# +# The Nerv utility functions Part of the [Nerv](../README.md) toolkit. -##Methods## +## Methods * __string = nerv.typename(obj a)__ A registered function, the original function is `luaT_lua_typename`. In some cases if you call `type(a)` for object of some class in __Nerv__(like __Nerv.CuMatrix__) it will only return "userdata"(because it is created in C), in this case you can use this method to get its type. @@ -14,4 +14,4 @@ A registered function, the original function is `luaT_newmetatable`, it returns * __string = nerv.setmetatable(table self, string tname)__ A registered function, the original function is `luaT_lua_setmetatable`. It assigns the metatable registered in __luaT__ by the name *tname* to the table *self*. And return *tname* to user. * __table = nerv.get_type(string typename)__ -Returns the type(`loadstring("return " .. typename)`).
\ No newline at end of file +Returns the type(`loadstring("return " .. typename)`). diff --git a/nerv/doc/nerv_class.md b/nerv/doc/nerv_class.md index 99f63e7..8314b12 100644 --- a/nerv/doc/nerv_class.md +++ b/nerv/doc/nerv_class.md @@ -1,10 +1,10 @@ -#The Nerv OOP# +# The Nerv OOP Part of the [Nerv](../README.md) toolkit. -##Methods## +## Methods * __metatable mt, metatable mpt = nerv.class(string tname, string parenttname)__ This method is used to create a class by the name `tname`, which inherits `parenttname` in __Nerv__, then you create a new instance of this class by calling `obj=tname(...)`. The `tname.__init(...)` method(if defined) will be called in the constructing. The metatable of the class and its parent class will be returned. -##Examples## +## Examples * This example implements a simple `nerv.Counter` class which is inherited by `nerv.BetterCounter`. ``` @@ -33,4 +33,4 @@ c1 = nerv.Counter(1) print(c1.c) bc1 = nerv.BetterCounter(1, 1) print(bc1.c, bc1.bc) -```
\ No newline at end of file +``` diff --git a/nerv/doc/nerv_io.md b/nerv/doc/nerv_io.md index 07589df..299362f 100644 --- a/nerv/doc/nerv_io.md +++ b/nerv/doc/nerv_io.md @@ -1,7 +1,7 @@ -#The Nerv IO Package# +# The Nerv IO Package Part of the [Nerv](../README.md) toolkit. -##Description## +## Description The main class that the user uses to store and read parameter object to and from files is __nerv.ChunkFile__. In the file, a parameter object will be saved using a standard format. First is the length(in byte) of this object, then a table which includes some meta information of the object, and a data area. Below is an example text file. ``` @@ -23,7 +23,7 @@ In the file, a parameter object will be saved using a standard format. First is 3.000000 3.000000 3.000000 ``` -##Methods## +## Methods * __ChunkFile ChunkFile(string fn, string mode)__ `mode` can be `r` or `w`, for reading or writing a file. The returned __ChunkFile__ will be ready to write or read objects which follows the __nerv.Param__ interface(using `write_chunk` and `read_chunk`). * __void ChunkFile.write_chunk(ChunkFile self, Param p)__ @@ -33,7 +33,7 @@ Read the __Param__ object by id `id` from the file `self`. It will be constructe * __void ChunkFile.close(ChunkFile self)__ Close the opened file. -##Examples## +## Examples * An example showing how to use __ChunkFile__ to store and read parameter objects. ``` require 'io' @@ -96,7 +96,7 @@ do end ``` -##Developer Notes## +## Developer Notes * There are four classes in to deal with chunk data, which are __nerv.ChunkFile__, __nerv.ChunkFileHandle__, __nerv.ChunkInfo__, __nerv.ChunkData__. Below is the underlying C structs. ``` typedef struct ChunkFileHandle { @@ -110,4 +110,5 @@ typedef struct ChunkData { char *data; } ChunkData; ``` -* In __Nerv.io__, a returned(by `ChunkFile.__init`) __nerv.ChunkFile__ will have a member `handle`, which is a __nerv.ChunkFileHandle__.
\ No newline at end of file + +* In __Nerv.io__, a returned(by `ChunkFile.__init`) __nerv.ChunkFile__ will have a member `handle`, which is a __nerv.ChunkFileHandle__. diff --git a/nerv/doc/nerv_layer.md b/nerv/doc/nerv_layer.md index de2fb12..dd7c9bb 100644 --- a/nerv/doc/nerv_layer.md +++ b/nerv/doc/nerv_layer.md @@ -1,9 +1,9 @@ -#The Nerv Layer Package# +# The Nerv Layer Package Part of the [Nerv](../README.md) toolkit. -##Description## +## Description __nerv.Layer__ is the base class and most of its methods are abstract. -###Class hierarchy and their members### +### Class hierarchy and their members * __nerv.Layer__. * `table dim_in` It specifies the dimensions of the inputs. * `table dim_out` It specifies the dimensions of the outputs. @@ -20,7 +20,7 @@ __nerv.Layer__ is the base class and most of its methods are abstract. * `int total_frams` Records how many frames have passed. * `bool compressed` The reference distribution can be a one-hot format. This feature is enabled by `layer_conf.compressed`. -##Methods## +## Methods * __void Layer.\_\_init(Layer self, string id, table global_conf, table layer_conf)__ Abstract method. The constructing method should assign `id` to `self.id` and `global_conf` to `self.gconf`, `layer_conf.dim_in` to `self.dim_in`, `layer_conf.dim_out` to `self.dim_out`. `dim_in` and `dim_out` are a list specifies the dimensions of the inputs and outputs. Also, `layer_conf` will include the parameters, which should also be properly saved. @@ -43,7 +43,7 @@ Check whether `#self.dim_in == len_in` and `#self.dim_out == len_out`, if violat Abstract method. The layer should return a list containing its parameters. -####nerv.Layer.get\_dim(self)#### +#### nerv.Layer.get\_dim(self) * Returns: `dim_in`: __table__. `dim_out`: __table__. @@ -52,7 +52,7 @@ The layer should return a list containing its parameters. * Description: Returns `self.dim_in, self.dim_out`. -##Examples## +## Examples * a basic example using __Nerv__ layers to a linear classification. ``` @@ -178,3 +178,4 @@ for l = 0, 10, 1 do end --[[end training]]-- ``` + diff --git a/nerv/doc/nerv_matrix.md b/nerv/doc/nerv_matrix.md index dfd843d..7555e6c 100644 --- a/nerv/doc/nerv_matrix.md +++ b/nerv/doc/nerv_matrix.md @@ -1,8 +1,8 @@ -#The Nerv Matrix Package# +# The Nerv Matrix Package Part of the [Nerv](../README.md) toolkit. -##Description## -###Underlying structure### +## Description +### Underlying structure In the begining is could be useful to know something about the underlying structure of a __Nerv__ matrix. Please keep in mind that matrice in __Nerv__ is row-major. Every matrix object is a encapsulation of a C struct that describes the attributes of this matrix. ``` @@ -20,12 +20,12 @@ typedef struct Matrix { It is worth mentioning that that `data_ref` is a counter which counts the number of references to its memory space, mind that it will also be increased when a row of the matrix is referenced(`col = m[2]`). A __Nerv__ matrix will deallocate its space when this counter is decreased to zero. Also note that all assigning operation in __Nerv__ is reference copy, you can use `copy_tod` or `copy_toh` method to copy value. Also, row assigning operations like `m1[2]=m2[3]` is forbidden in __Nerv__. -###Class hierarchy### +### Class hierarchy The class hierarchy of the matrix classes can be clearly observed in `matrix/init.c`. First there is a abstract base class __Nerv.Matrix__, which is inherited by __Nerv.CuMatrix__ and __Nerv.MMatrix__(also abstract). Finally, there is __Nerv.CuMatrixFloat__, __Nerv.CuMatrixDouble__, inheriting __Nerv.CuMatrix__, and __Nerv.MMatrixFloat__, __Nerv.MMatrixDouble__, __Nerv.MMatrixInt__ , inheriting __Nerv.MMatrix__. -##Methods## +## Methods Mind that usually a matrix object can only do calculation with matrix of its own type(a __Nerv.CuMatrixFloat__ matrix can only do add operation with a __Nerv.CuMatrixFloat__). In the methods description below, __Matrix__ could be __Nerv.CuMatrixFloat__, __Nerv.CuMatrixDouble__, __Nerv.MMatrixFloat__ or __Nerv.MMatrixDouble__. __Element_type__ could be `float` or `double`, respectively. * __Matrix = Matrix(int nrow, int ncol)__ @@ -113,7 +113,7 @@ Write `self` to the file position in `chunk`. * __void MMatrix.copy_from(MMatrix ma, MMatrix mb,[int b_bgein, int b_end, int a_begin])__ Copy a part of `mb`(rows of index `[b_begin..b_end)`) to `ma` beginning at row index `a_begin`. If not specified, `b_begin` will be `0`, `b_end` will be `b.nrow`, `a_begin` will be `0`. -##Examples## +## Examples * Use `get_dataref_value` to test __Nerv__'s matrix space allocation. ``` m = 10 @@ -134,6 +134,7 @@ print("test fm:get_dataref_value:", fm:get_dataref_value()) print(fm) print(dm) ``` + * Test some __Matrix__ calculations. ``` m = 4 @@ -167,3 +168,4 @@ print(a) a:log_elem(fs) print(a) ``` + diff --git a/nerv/doc/nerv_nn.md b/nerv/doc/nerv_nn.md index c57447d..63537fb 100644 --- a/nerv/doc/nerv_nn.md +++ b/nerv/doc/nerv_nn.md @@ -1,19 +1,19 @@ -#The Nerv NN Package# +# The Nerv NN Package Part of the [Nerv](../README.md) toolkit. -##Description## -###Class hierarchy### +## Description +### Class hierarchy it contains __nerv.LayerRepo__, __nerv.ParamRepo__, and __nerv.DAGLayer__(inherits __nerv.Layer__). -###Class hierarchy and their members### -####nerv.ParamRepo#### +### Class hierarchy and their members +#### nerv.ParamRepo Get parameter object by ID. * `table param_table` Contains the mapping of parameter ID to parameter file(__nerv.ChunkFile__) * __nerv.LayerRepo__ Get layer object by ID. * `table layers` Contains the mapping of layer ID to layer object. objects. -####__nerv.DAGLayer__#### +#### __nerv.DAGLayer__ Inherits __nerv.Layer__. * `layers`: __table__, a mapping from a layer ID to its "ref". A ref is a structure that contains reference to space allocations and other info of the layer. * `inputs`: __table__, a mapping from the inputs ports of the DAG layer to the input ports of the sublayer, the key is the port number, the value is `{ref, port}`. @@ -21,17 +21,17 @@ Inherits __nerv.Layer__. * `parsed_conn`: __table__, a list of parsed connections, each entry is of format `{{ref_from, port_from}, {ref_to, port_to}}`. * `queue`: __table__, a list of "ref"s, the propagation of the DAGLayer will follow this order, and back-propagation will follow a reverse order. -##Methods## +## Methods -###__nerv.ParamRepo__### +### __nerv.ParamRepo__ -####nerv.ParamRepo:\_\_init(param\_files)#### +#### nerv.ParamRepo:\_\_init(param\_files) * Parameters: `param_files`: __table__ * Description: `param_files` is a list of file names that stores parameters, the newed __ParamRepo__ will read them from file and store the mapping for future fetching. -####nerv.Param ParamRepo.get_param(ParamRepo self, string pid, table global_conf)#### +#### nerv.Param ParamRepo.get_param(ParamRepo self, string pid, table global_conf) * Returns: __nerv.Layer__ * Parameters: @@ -41,8 +41,8 @@ Inherits __nerv.Layer__. * Description: __ParamRepo__ will find the __nerv.ChunkFile__ `pf` that contains parameter of ID `pid` and return `pf:read_chunk(pid, global_conf)`. -###__nerv.LayerRepo__### -####nerv.LayerRepo:\_\_init(layer\_spec, param\_repo, global\_conf)#### +### __nerv.LayerRepo__ +#### nerv.LayerRepo:\_\_init(layer\_spec, param\_repo, global\_conf) * Returns: __nerv.LayerRepo__. * Parameters: @@ -60,7 +60,7 @@ Inherits __nerv.Layer__. __LayerRepo__ will merge `param_config` into `layer_config` and construct a layer by calling `layer_type(layerid, global_conf, layer_config)`. -####nerv.LayerRepo.get\_layer(self, lid)#### +#### nerv.LayerRepo.get\_layer(self, lid) * Returns: __nerv.LayerRepo__, the layer with ID `lid`. * Parameters: @@ -69,8 +69,8 @@ Inherits __nerv.Layer__. * Description: Returns the layer with ID `lid`. -###nerv.DAGLayer### -####nerv.DAGLayer:\_\_init(id, global\_conf, layer\_conf)#### +### nerv.DAGLayer +#### nerv.DAGLayer:\_\_init(id, global\_conf, layer\_conf) * Returns: __nerv.DAGLayer__ * Parameters: @@ -89,7 +89,7 @@ Inherits __nerv.Layer__. }}) ``` -####nerv.DAGLayer.init(self, batch\_size)#### +#### nerv.DAGLayer.init(self, batch\_size) * Parameters: `self`: __nerv.DAGLayer__ `batch_size`: __int__ @@ -97,7 +97,7 @@ Inherits __nerv.Layer__. This initialization method will allocate space for output and input matrice, and will call `init()` for each of its sub layers. -####nerv.DAGLayer.propagate(self, input, output)#### +#### nerv.DAGLayer.propagate(self, input, output) * Parameters: `self`: __nerv.DAGLayer__ `input`: __table__ @@ -105,7 +105,7 @@ Inherits __nerv.Layer__. * Description: The same function as __nerv.Layer.propagate__, do propagation for each layer in the order of `self.queue`. -####nerv.DAGLayer.back\_propagate(self, next\_bp\_err, bp\_err, input, output)#### +#### nerv.DAGLayer.back\_propagate(self, next\_bp\_err, bp\_err, input, output) * Parameters: `self`: __nerv.DAGLayer__ `next_bp_err`: __table__ @@ -115,7 +115,7 @@ Inherits __nerv.Layer__. * Description: The same function as __nerv.Layer.back_propagate__, do back-propagation for each layer in the reverse order of `self.queue`. -####nerv.DAGLayer.update(self, bp\_err, input, output)#### +#### nerv.DAGLayer.update(self, bp\_err, input, output) * Parameters: `self`: __nerv.DAGLayer__ `bp_err`: __table__ @@ -124,7 +124,7 @@ Inherits __nerv.Layer__. * Description: The same function as __nerv.Layer.update__, do update for each layer in the order of `self.queue`. -##Examples## +## Examples * aaa ``` @@ -253,4 +253,5 @@ for l = 0, 10, 1 do ce_last = softmaxL.total_ce end --[[end training]]-- -```
\ No newline at end of file +``` + diff --git a/nerv/doc/nerv_param.md b/nerv/doc/nerv_param.md index 167cb11..98793f0 100644 --- a/nerv/doc/nerv_param.md +++ b/nerv/doc/nerv_param.md @@ -1,17 +1,17 @@ -#The Nerv Parameter Package# +# The Nerv Parameter Package Part of the [Nerv](../README.md) toolkit. -##Description## -###Class hierarchy### +## Description +### Class hierarchy There is a base class __Nerv.Param__ defined in `layer/init.lua`. -###Class hierarchy and their members### +### Class hierarchy and their members * __nerv.MatrixParam__ inherits __nerv.Param__ * `Matrix trans` stores the parameter matrix. * __nerv.LinearTransParam__ inherits __Nerv.MatrixParam__. * __Nerv.BiasParam__ inherits __Nerv.MatrixParam__. -##Methods## +## Methods * __void Param.\_\_init(Param self, string id, table global_conf)__ Constructor of a __Param__, it will set `self.id` to be `id` and `self.gconf` to be `global_conf`. * __void Param.set_info(Param self, table info)__ |